Boundary-based lower-bound functions for dynamic time warping and their indexing

Lower-bound functions are crucial for indexing time-series data tinder Dynamic Time Warping (DTW) distance. In this paper, we propose a unified framework to explain the existing lower-bound functions. Based on the framework, we further propose a group of lower-bound functions for DTW and investigate their performances through extensive experiments. Experimental results show that the new lower-bound functions are better than the existing one in most cases. An index structure based on the new lower-bound functions is also implemented.